Video-Text-to-Text
Transformers
Safetensors
English
qwen2
text-generation
multimodal
custom_code
text-generation-inference
Instructions to use BAAI/Video-XL-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BAAI/Video-XL-2 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BAAI/Video-XL-2", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("BAAI/Video-XL-2", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
Out of Mem for 4090-24G
#1
by GUESSGUO - opened
For current infer code, how much gpu mem is required? 24G seems unavailable.
For current infer code, how much gpu mem is required? 24G seems unavailable.
Thanks for your comment : ) The code is currently only optimized for 80GB GPUs. We’ll be releasing the full inference code later today — please stay tuned!
wen full inference code?